Results for Real2Sim
Each action below, shows the video, and corresponding segmentation masks and neural renderer outputs for the three methods.
- A. Ground-truth boxes, ground-truth action phase
- B. Ground-truth boxes, predicted action phase
- C. Predicted boxes, predicted action phase
Action 1: Pull left to right
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 8675 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 13956 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 6848 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 20193 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 10960 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 15606 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
Action 2: Pull right to left
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 13309 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 3107 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 11240 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 2458 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 10116 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 11732 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
Action 3: Push left to right
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 3694 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 601 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 9889 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 4018 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 6955 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 6132 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
Action 4: Push right to left
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 3949 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 1987 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 4218 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 4378 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 1040 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 8844 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
Action 5: Pick up
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 7194 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 38559 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 12359 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 1838 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 2875 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 24925 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
Action 6: Put behind
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 1044 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 6538 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 3074 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 12986 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 779 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 4388 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
Action 7: Put in front of
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 1663 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 41177 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 28603 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 5967 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 14841 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 2114 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
Action 8: Put next to
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 4053 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 19 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 874 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 3340 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 1890 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 1642 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
Action 9: Put onto
ID | Video | Method A | Method B | Method C |
---|---|---|---|---|
Vid 1: 8801 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 2: 7655 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 3: 13390 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 4: 757 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 5: 7504 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
|
Vid 6: 16310 | ![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |
![]() Segmentation mask ![]() Renderer output |